jevbooks

← All projects

system_one_client

schainks/system_one_client

Elixir client for System One decision models, including TypeSafe Jev.

Classification & Routing0.56Runner-up: Infra / SDKs / IntegrationsQuestionnaire
Automated README summary

Automatically summarized from the README on 13 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

An Elixir client that sends a state and typed questions to System One decision models and returns full probability distributions. It supports TypeSafe Jev, Cloudflare Clef, OpenAI Decisions, OpenRouter, and self-hosted endpoints, for routing and gating decisions.

How it uses Jev

Jev is one of the supported providers. You call SystemOneClient.evaluate(state, questions) with typed questions (noul, choice, score). Jev returns calibrated probabilities, e.g. a Choice answer with confidence and probabilities, a Noul answer with a noul value, or a Score answer with score and probabilities. The result is used in code for top-k, thresholds, or level cuts.

Primitives:choicescorenoul

Technique worth stealing

Use full probability distributions from typed questions for routing and gating decisions.

Try it

Add {:system_one_client, "~> 0.1"} to deps, then call SystemOneClient.evaluate/3.

View on GitHub

Start using Jev: API key and your first request →

Model judgments from README excerpts

Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.

Models & evaluation dates

Inclusion gate
jev-1.13.0
Project signals
jev-1.13.0
Category
jev-1.13.0
Pattern tags
jev-1.13.0

Evidence

These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.

  • Jev is core to the projectnot found in the excerpt0.08
  • Shows a System One patternFound in material0.81
  • Describes handling uncertaintynot found in the excerpt0.12
  • Reports measured numbersnot found in the excerpt0.05
  • Is a runnable toolFound in material0.92
  • Top-10 learning shortlist signalunclear0.43
  • Is a replica of the modelnot found in the excerpt0.03
  • Solves a common problem (0–2)score on a 0–2 scale1.22 / 2
  • About JevFound in material0.98
Signals
Jev is core to the project0.08Shows a System One pattern0.81Describes handling uncertainty0.12Reports measured numbers0.05Is a runnable tool0.92Top-10 learning shortlist signal0.43Is a replica of the model0.0300.51Solves a common problem (0–2)1.22 / 2012

no-judgment band (0.40–0.60)

Design patterns
Questionnaire0.95Traffic light0.41Fail open, fail closed0.29Blind review0.2400.51

no-judgment band (0.40–0.60)

The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 13 Oct 2026.